It’s possible that I shall make an ass of myself. But in that case one can always get out of it with a little dialectic. I have, of course, so worded my proposition as to be right either way (K.Marx, Letter to F.Engels on the Indian Mutiny)
Thursday, September 04, 2025
Protecting against data leaks in large ai models: ERC grant for CISPA researcher
The ERC Starting Grant is one of the most prestigious awards for early-career researchers in Europe. It supports fundamental research with high innovation potential. “Receiving this grant is, for me personally, confirmation that basic research is worthwhile for both society and technology, and that trust in artificial intelligence is only possible with real data protection,” says Franziska Boenisch. But it is precisely this data protection that is difficult to guarantee—especially for large AI models like GPT or LLaMA. These so-called foundation models are fed massive, uncurated datasets during pretraining, which can include highly sensitive material such as our emails or private conversations with systems like ChatGPT. During fine-tuning, the models are adapted to specific tasks—for example, customer service or medical diagnostics—where sensitive data can also enter the models. This is how powerful systems for image, audio, and text generation are created. The downside: They can unintentionally disclose private information. That’s exactly what Boenisch is tackling: “My project develops new methods so that foundation models do not unintentionally leak private training data. I make sure this data stays protected and that we can detect when there is a problem,” she explains.
AI as the “new Google”
What particularly attracts Boenisch to this topic is AI’s growing importance in everyday life: “For many people, foundation models have already become the new Google. They’re used for all sorts of questions, including very personal ones.” Protecting private information is therefore not only a technical issue but also a societal one: “The worst part is when we don’t even notice that a model is leaking data—because anything that becomes public once stays public forever. And that is exactly the risk right now. Current methods are not reliable at detecting and preventing data leaks. My project develops new approaches to close this gap and makes visible where risks exist.” The ERC grant opens up new opportunities for the researcher: “For me, the ERC is a huge opportunity. Thanks to this funding I can build a strong research team that is fully dedicated to an issue that affects all of us: protecting our data in an AI world.”
A new approach: data protection across the entire AI lifecycle
According to Boenisch, existing methods for preventing data leaks often only act in isolated phases of the training process or lead to drops in model quality. Her project therefore goes several steps further: “For the first time, my approach provides a theoretical privacy guarantee across the entire lifecycle of foundation models—not just for individual stages like fine-tuning, as has been the case until now. I’m making pretraining privacy protection practical, without the huge reductions in model prediction quality that earlier methods caused.” Preserving model efficiency is only one of the big challenges Boenisch faces. The question of societal and legal oversight of AI models is also part of her research project: “I am extending the methodological work by developing new auditing tools, and for the first time my auditing links technical risks—such as the success rate of certain attacks—directly to privacy risks under the GDPR, thereby connecting our technical capabilities with legal and societal requirements.”
About the ERC
The ERC, set up by the European Union in 2007, is the premier European funding organisation for excellent frontier research. It funds creative researchers of any nationality and age, to run projects based across Europe. The ERC offers 4 core grant schemes: Starting Grants, Consolidator Grants, Advanced Grants and Synergy Grants. With its additional Proof of Concept Grant scheme, the ERC helps grantees to explore the innovation potential of their ideas or research results. The ERC is led by an independent governing body, the Scientific Council. Since 1 November 2021, Maria Leptin is the President of the ERC.
New study links grain foods to healthier diet patterns, metabolic health and everyday accessibility
National diet analysis finds that both whole and refined grain foods can contribute to improved dietary patterns and health
Grain foods linked to healthier diet patterns, improved metabolic health and greater everyday accessibility, according to a new study from the University of Washington.
WASHINGTON – Sept. 4, 2025 – With so much confusion around what makes a grain food truly healthy, new research now offers a clearer picture: a combination of grain foods can support better nutrition and metabolic health when they deliver on nutrient density. A new study published in Nutrients, which analyzed the diets of more than 14,000 Americans over five years, found that both whole and refined grain foods play a role in improved diet quality, nutrient intake and everyday accessibility.
Conducted by researchers at the Center for Public Health Nutrition at the University of Washington, the peer-reviewed study analyzed data from the National Health and Nutrition Examination Survey (NHANES) from 2017 to 2023. The analysis found that many everyday grain foods – including some breads, cereals and tortillas – ranked surprisingly high for nutrient density and affordability. The findings offer a more nuanced view of grain foods, moving beyond assumptions and highlighting a broader range of options that can support health.
Using two new nutrient profiling models to evaluate carbohydrate quality and overall nutrient density, the Carbohydrate Food Quality Score CFQS-3 and the Nutrient Rich Food (NRF9.3) index, the study identified which grain foods qualify as “healthy grain foods” based on higher levels of fiber, protein and essential nutrients, and lower amounts of added sugars, saturated fat and sodium. This approach revealed that both whole and refined grain foods can meet the mark, contributing meaningfully to diet quality and health. People who consumed more of these healthy grain foods had better overall nutrient intake, healthier eating patterns and more favorable markers of metabolic health.
Key findings include:
Improved diet quality and nutrient intake. People who consumed more healthy grain foods had better overall diet quality and higher intakes of fiber, protein, iron, calcium, potassium and magnesium.
Includes both whole and refined grain foods. Both types scored highly for nutrient density, with many refined or enriched options – like certain breads, cereals and tortillas – delivering strong nutritional value alongside whole grain choices.
Part of healthier overall eating patterns. People who ate the most healthy grain foods also consumed more fruits, vegetables and lean proteins, suggesting these grain foods may support or reflect broader healthy habits.
Linked to better metabolic health. Adults with higher intakes of these grain foods were less likely to be obese and had lower fasting insulin levels, a key marker of metabolic function.
No added cost. Healthy grain foods were no more expensive than less healthy options and were often more affordable per gram or calorie.
“Healthy grains are a critical component of healthy diets" said Dr. Adam Drewnowski, Professor of Epidemiology at the University of Washington. “Our evaluation took whole grain content into account, along with fiber, vitamins and minerals. By delivering key nutrients such as fiber, iron, B vitamins and folate, grain foods can make a meaningful contribution to healthier eating patterns among all population groups.”
As nutrition guidance continues to evolve, this study adds important clarity around the role of grain foods in supporting public health. The findings highlight the value of balance – not just in overall eating patterns, but in the types of grain foods we include. Recognizing the nutritional contributions of both whole and refined/enriched options offers a more inclusive and realistic path to better outcomes for Americans’ diet and overall health. To learn more, visit GrainFoodsFoundation.org.
This study was supported through an unrestricted grant from the Grain Foods Foundation (GFF), a nonprofit organization dedicated to nutrition science and education to better understand the role of grain foods in healthful diets. GFF had no influence over the study design, data analysis or interpretation of findings.
About the Study
The study analyzed dietary intake data from more than 14,000 individuals aged 6 and older using five cycles of the National Health and Nutrition Examination Survey (NHANES) from 2017 to 2023. Grain foods were evaluated using two new nutrient profiling models – CFQS-3 and NRF9.3g – and categorized as higher or lower quality based on nutrient density. Researchers then assessed associations between grain quality and overall diet quality, nutrient intake, affordability and select metabolic health indicators, including obesity and fasting insulin.
About Grain Foods Foundation
Formed in 2004, Grain Foods Foundation (GFF) is committed to science-based, grains-positive programming, bringing a drumbeat of communications about the role of grain foods in a well-balanced eating pattern. GFF provides a comprehensive communications framework, conference participation, webinars, fact-based digital tools and a robust voice on social media for GFF investors and the entire spectrum of health influencers. GFF is funded by grain foods manufacturers, flour millers and members of the allied trades. For more information about the Grain Foods Foundation, visit www.grainfoodsfoundation.org.
Healthy Grains in Healthy Diets: The Contribution of Grain Foods to Diet Quality and Health in the National Health and Nutrition Examination Survey 2017–2023
Article Publication Date
COI Statement
This study was supported through an unrestricted grant from the Grain Foods Foundation (GFF), a nonprofit organization dedicated to nutrition science and education to better understand the role of grain foods in healthful diets. GFF had no influence over the study design, data analysis or interpretation of findings.
Two ERC Grants for Goethe University: Why a sharks becomes extinct and how to study the dynamics of biomolecules
New research projects at Goethe University are investigating the reasons for the extinction of prehistoric shark species and developing a new method for analysis of large biomolecules using nuclear magnetic resonance spectroscopy
Credit: Juergen Lecher for Goethe University Frankfurt
FRANKFURT. Professor Enrico Schleiff, President of Goethe University, congratulated the two researchers: “The research projects of Jeremy McCormack and Andrei Kuzhelev are impressive examples of how we at Goethe University continue to push the boundaries of what can still be measured—whether it is atomic traces of sharks’ diets preserved in their teeth, or an innovative spectroscopic tool for investigating the dynamics of large biomolecules. I am delighted that the European Research Council is funding these forward-looking projects.”
SHARKS: In the midst of the sixth great mass extinction in Earth’s history – today – geoscientist Dr. Jeremy McCormack is focusing in his ERC project on sharks, a quarter of whose species are threatened with extinction, mainly due to overfishing. Using new methods for analyzing zinc, calcium, and nitrogen isotopes in fossil teeth of various prehistoric shark species, he is investigating how the ecology and especially the diet of these predators may have contributed to their extinction. This is possible because the ratio of different isotopes within their teeth shifts depending on the level of the food chain from which a shark’s prey originated. These insights are expected to shed light on the causes of extinction of prehistoric shark species and contribute to conservation strategies for today’s endangered sharks.
LiquidStateDNP: In his ERC project, Dr. Andrei Kuzhelev will develop nuclear magnetic resonance (NMR) spectroscopy for biomolecule solutions at a nanoliter scale. For this, he is using a specialized NMR technique – Liquid-State Dynamic Nuclear Polarization (DNP) – available at the Biomolecular Magnetic Resonance Center (BMRZ) at Goethe University, which offers globally unique analytical possibilities: Unlike similar methods, which require shock-freezing of biomaterial samples, it allows the study of even the smallest sample quantities in liquid phase, much closer to their natural state. Kuzhelev will significantly advance this method to reveal not only the structures and dynamics of small, but also of large, complex biomolecules – a decisive technological step forward for various applications ranging from materials science to the development of medical drugs.
ERC Starting Grants support outstanding researchers in the first years after their doctorate who wish to establish their own research team and gain a foothold in the scientific community with a promising research project. For their projects, they receive up to 1.5 million euros over a period of up to five years.
The European Research Council (ERC) is a body established by the European Commission to fund frontier-oriented basic research.
Broccoli seeds can spread resistance to multiple fungicides
Researchers screened commercial broccoli seeds for Alternaria brassicicola, a fungal pathogen.
They found that seeds can harbor A. brassicicola and can spread resistance to multiple fungicides that growers use to try to manage A. brassicicola.
Based on the findings, the researchers developed a faster way for detecting and monitoring fungicide resistance.
Washington, D.C.—A new study found evidence that commercial broccoli seeds can harbor a fungal seedborne pathogen, Alternaria brassicicola, with cross resistance to 2 commonly used fungicides. The finding highlights the need to include fungicide resistance screening in seed health testing programs where appropriate and practical to improve sustainable disease management. The study was published in Applied and Environmental Microbiology, a journal of the American Society for Microbiology.
“Our study highlights the importance of seed health testing for the presence of A. brassicicola in brassica seeds, particularly broccoli,” said corresponding study author Bhabesh Dutta, Ph.D., professor and extension vegetable pathologist at the University of Georgia. “This will help to remove contaminated seedlots and potentially reduce dissemination of fungicide resistant isolates locally as well as globally. Ideally, incorporating screening for the presence of the pathogen along with their fungicide profile would greatly improve the quality of seed health testing and promote high-quality seeds available for our growers.”
A. brassicicola is resistant to commonly used fungicides and affects the quality and marketability of broccoli heads, especially during warm and humid weather. In recent years, growers have seen reduced efficacy of fungicides for broccoli crops, which raised concern about the emergence of issues linked with resistant fungal populations. In the new study, the researchers tested the efficacy of 3 commonly used SDHI (succinate dehydrogenase inhibitor) fungicides that are commonly used by growers to manage this pathogen: boscalid, penthiopyrad and fluopyram.
The researchers screened commercial seeds of 2 commonly grown broccoli cultivars for the presence of A. brassicicola. The pathogen isolates were screened against the 3 commonly used SDHI fungicides under in vitro conditions. First, the researchers performed a lab-based assay to screen the isolates with different doses to evaluate their sensitivity. Then they examined the fungus at the molecular level by looking at mutations in SDHI genes known to be linked to fungicide resistance.
They found that seeds can act as a carrier of A. brassicicola with resistance to boscalid and penthiopyrad, indicating potential introduction of fungicide resistance via seeds. Some of the seed isolates were also resistant to a commonly used fungicide with a completely different mode of action (Quinone-outside inhibitor; azoxystrobin). This is the first report of the occurrence of multiple fungicide resistance in A. brassicicola from naturally infested seeds. The researchers also found that 93% of the pathogen population that displayed resistance at the phenotypic level also had point mutations that confer resistance to boscalid and penthiopyrad. This strong link between lab results and genetic markers confirms that resistance could potentially be widespread and likely stable in the population.
“These findings demonstrate that seeds can serve as a source for the potential introduction of resistant fungal populations in areas where these fungicides have never been used, resulting in reduced options for growers,” Dutta said.
Based on the mutation the researchers discovered, the scientists developed a PCR-based allele-specific assay that can be used for rapid detection and monitoring of fungicide resistance. “This tool can help regulatory agencies and seed industries to detect SDHI-resistance in seedborne A. brassicicola and make informed decisions early,” Dutta said.
Dutta’s lab group led the study with post-doctoral associates Navjot Kaur, Ph.D., and Anoop Malik, Ph.D. This study was part of a multistate U.S. Department of Agriculture and National Institute of Food and Agriculture project on Alternaria leaf blight and head rot in broccoli funded through the Specialty Crops Research Initiative Program (USDA NIFA SCRI; 2020-51181-32062).
###
The American Society for Microbiology is one of the largest professional societies dedicated to the life sciences and is composed of over 37,000 scientists and health practitioners. ASM's mission is to promote and advance the microbial sciences.
ASM advances the microbial sciences through conferences, publications, certifications, educational opportunities and advocacy efforts. It enhances laboratory capacity around the globe through training and resources. It provides a network for scientists in academia, industry and clinical settings. Additionally, ASM promotes a deeper understanding of the microbial sciences to all audiences.
Journal
Applied and Environmental Microbiology
New AI tool addresses accuracy and fairness in data to improve health algorithms
Detects biases in the datasets used to train machine-learning algorithms
The Mount Sinai Hospital / Mount Sinai School of Medicine
Credit: Gulamali, et al., Journal of Medical Internet Research
New York, NY [September 4, 2025]—A team of researchers at the Icahn School of Medicine at Mount Sinai has developed a new method to identify and reduce biases in datasets used to train machine-learning algorithms—addressing a critical issue that can affect diagnostic accuracy and treatment decisions. The findings were published in the September 4 online issue of the Journal of Medical Internet Research [DOI: 10.2196/71757].
To tackle the problem, the investigators developed AEquity, a tool that helps detect and correct bias in health care datasets before they are used to train artificial intelligence (AI) and machine-learning models. The investigators tested AEquity on different types of health data, including medical images, patient records, and a major public health survey, the National Health and Nutrition Examination Survey, using a variety of machine-learning models. The tool was able to spot both well-known and previously overlooked biases across these datasets.
AI tools are increasingly used in health care to support decisions, ranging from diagnosis to cost prediction. But these tools are only as accurate as the data used to train them. Some demographic groups may not be proportionately represented in a dataset. In addition, many conditions may present differently or be overdiagnosed across groups, the investigators say. Machine-learning systems trained on such data can perpetuate and amplify inaccuracies, creating a feedback loop of suboptimal care, such as missed diagnoses and unintended outcomes.
“Our goal was to create a practical tool that could help developers and health systems identify whether bias exists in their data—and then take steps to mitigate it,” says first author Faris Gulamali, MD. “We want to help ensure these tools work well for everyone, not just the groups most represented in the data.”
The research team reported that AEquity is adaptable to a wide range of machine-learning models, from simpler approaches to advanced systems like those powering large language models. It can be applied to both small and complex datasets and can assess not only the input data, such as lab results or medical images, but also the outputs, including predicted diagnoses and risk scores.
The study’s results further suggest that AEquity could be valuable for developers, researchers, and regulators alike. It may be used during algorithm development, in audits before deployment, or as part of broader efforts to improve fairness in health care AI.
“Tools like AEquity are an important step toward building more equitable AI systems, but they’re only part of the solution,” says senior corresponding author Girish N. Nadkarni, MD, MPH, Chair of the Windreich Department of Artificial Intelligence and Human Health, Director of the Hasso Plattner Institute for Digital Health, and the Irene and Dr. Arthur M. Fishberg Professor of Medicine at the Icahn School of Medicine at Mount Sinai, and the Chief AI Officer of the Mount Sinai Health System. “If we want these technologies to truly serve all patients, we need to pair technical advances with broader changes in how data is collected, interpreted, and applied in health care. The foundation matters, and it starts with the data.”
“This research reflects a vital evolution in how we think about AI in health care—not just as a decision-making tool, but as an engine that improves health across the many communities we serve,” says David L. Reich MD, Chief Clinical Officer of the Mount Sinai Health System and President of The Mount Sinai Hospital. “By identifying and correcting inherent bias at the dataset level, we’re addressing the root of the problem before it impacts patient care. This is how we build broader community trust in AI and ensure that resulting innovations improve outcomes for all patients, not just those best represented in the data. It’s a critical step in becoming a learning health system that continuously refines and adapts to improve health for all.”
The paper is titled “Detecting, Characterizing, and Mitigating Implicit and Explicit Racial Biases in Health Care Datasets With Subgroup Learnability: Algorithm Development and Validation Study.”
The study’s authors, as listed in the journal, are Faris Gulamali, Ashwin Shreekant Sawant, Lora Liharska, Carol Horowitz, Lili Chan, Patricia Kovatch, Ira Hofer, Karandeep Singh, Lynne Richardson, Emmanuel Mensah, Alexander Charney, David Reich, Jianying Hu, and Girish Nadkarni.
The study was funded by the National Center for Advancing Translational Sciences and the National Institutes of Health.
About Mount Sinai's Windreich Department of AI and Human Health
Led by Girish N. Nadkarni, MD, MPH—an international authority on the safe, effective, and ethical use of AI in health care—Mount Sinai’s Windreich Department of AI and Human Health is the first of its kind at a U.S. medical school, pioneering transformative advancements at the intersection of artificial intelligence and human health.
The Department is committed to leveraging AI in a responsible, effective, ethical, and safe manner to transform research, clinical care, education, and operations. By bringing together world-class AI expertise, cutting-edge infrastructure, and unparalleled computational power, the department is advancing breakthroughs in multi-scale, multimodal data integration while streamlining pathways for rapid testing and translation into practice.
The Department benefits from dynamic collaborations across Mount Sinai, including with the Hasso Plattner Institute for Digital Health at Mount Sinai—a partnership between the Hasso Plattner Institute for Digital Engineering in Potsdam, Germany, and the Mount Sinai Health System—which complements its mission by advancing data-driven approaches to improve patient care and health outcomes.
At the heart of this innovation is the renowned Icahn School of Medicine at Mount Sinai, which serves as a central hub for learning and collaboration. This unique integration enables dynamic partnerships across institutes, academic departments, hospitals, and outpatient centers, driving progress in disease prevention, improving treatments for complex illnesses, and elevating quality of life on a global scale.
In 2024, the Department's innovative NutriScan AI application, developed by the Mount Sinai Health System Clinical Data Science team in partnership with Department faculty, earned Mount Sinai Health System the prestigious Hearst Health Prize. NutriScan is designed to facilitate faster identification and treatment of malnutrition in hospitalized patients. This machine learning tool improves malnutrition diagnosis rates and resource utilization, demonstrating the impactful application of AI in health care.
For more information on Mount Sinai's Windreich Department of AI and Human Health, visit: ai.mssm.edu.
About the Hasso Plattner Institute at Mount Sinai
At the Hasso Plattner Institute for Digital Health at Mount Sinai, the tools of data science, biomedical and digital engineering, and medical expertise are used to improve and extend lives. The Institute represents a collaboration between the Hasso Plattner Institute for Digital Engineering in Potsdam, Germany, and the Mount Sinai Health System.
Under the leadership of Girish Nadkarni, MD, MPH, who directs the Institute, and Professor Lothar Wieler, a globally recognized expert in public health and digital transformation, they jointly oversee the partnership, driving innovations that positively impact patient lives while transforming how people think about personal health and health systems.
The Hasso Plattner Institute for Digital Health at Mount Sinai receives generous support from the Hasso Plattner Foundation. Current research programs and machine learning efforts focus on improving the ability to diagnose and treat patients.
About the Icahn School of Medicine at Mount Sinai
The Icahn School of Medicine at Mount Sinai is internationally renowned for its outstanding research, educational, and clinical care programs. It is the sole academic partner for the seven member hospitals* of the Mount Sinai Health System, one of the largest academic health systems in the United States, providing care to New York City’s large and diverse patient population.
The Icahn School of Medicine at Mount Sinai offers highly competitive MD, PhD, MD-PhD, and master’s degree programs, with enrollment of more than 1,200 students. It has the largest graduate medical education program in the country, with more than 2,600 clinical residents and fellows training throughout the Health System. Its Graduate School of Biomedical Sciences offers 13 degree-granting programs, conducts innovative basic and translational research, and trains more than 560 postdoctoral research fellows.
Ranked 11th nationwide in National Institutes of Health (NIH) funding, the Icahn School of Medicine at Mount Sinai is among the 99th percentile in research dollars per investigator according to the Association of American Medical Colleges. More than 4,500 scientists, educators, and clinicians work within and across dozens of academic departments and multidisciplinary institutes with an emphasis on translational research and therapeutics. Through Mount Sinai Innovation Partners (MSIP), the Health System facilitates the real-world application and commercialization of medical breakthroughs made at Mount Sinai.
* Mount Sinai Health System member hospitals: The Mount Sinai Hospital; Mount Sinai Brooklyn; Mount Sinai Morningside; Mount Sinai Queens; Mount Sinai South Nassau; Mount Sinai West; and New York Eye and Ear Infirmary of Mount Sinai
Detecting, Characterizing, and Mitigating Implicit and Explicit Racial Biases in Health Care Datasets With Subgroup Learnability: Algorithm Development and Validation
